摘要
高分辨率遥感图像内容复杂,细节信息丰富,传统的浅层特征在描述这类图像上存在一定难度,容易导致检索中存在较大的语义鸿沟。本文将大规模数据集ImageNet上预训练的4种不同卷积神经网络用于遥感图像检索,首先分别提取4种网络中不同层次的输出值作为高层特征,再对高层特征进行高斯归一化,然后采用欧氏距离作为相似性度量进行检索。在UC-Merced和WHU-RS数据集上的一系列实验结果表明,4种卷积神经网络的高层特征中,以CNN-M特征的检索性能最好;与视觉词袋和全局形态纹理描述子这两种浅层特征相比,高层特征的检索平均准确率提高了15.7%~25.6%,平均归一化修改检索等级减少了17%~22.1%。因此将ImageNet上预训练的卷积神经网络用于遥感图像检索是一种有效的方法。
High resolution remote sensing images have complicated content and abundant detail information.Large semantic gaps will occur as such images are difficult to describe using traditional shallow features.This paper proposes a method using four different CNNs pre-trained on ImageNet to in remote sensing image retrieval.High-level features are extracted from different layers of the four CNNs.A Gaussian normalization method is adopted to normalize high-level features,and Euclidean distance is used as the similarity measurement.A serial of experiments carried on the UC-Merced and WHU-RS datasets show that CNN-M feature achieves the best retrieval performance with CNN features.Compared with the visual bag of words and global morphological texture descriptors,the mean average precision of CNN features was 15.7%-25.6% higher than that of shallow features.The average normalizedmodified retrieval rank of CNN features was 17%-22.1% lower than that of shallow features.Therefore the pre-trained convolutional neural network is effective for high-resolution remote sensing image retrieval.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2018年第1期67-73,共7页
Geomatics and Information Science of Wuhan University
基金
国家自然科学基金(41261091)
江西省教育厅科技项目(GJJ13482)
江西省自然科学基金(20151BAB207062)~~
关键词
遥感图像
检索
卷积神经网路
预训练
remote sensing image
retrieval
convolutional neural networks
pre-trained
